With the advent of large multimodal foundation models such as ChatGPT, Gemini, Claude, and DeepSeek, scientific research stands at the threshold of an AI-based technological transformation. Recent surveys indicate that the majority of researchers anticipate AI will become mainstream in scientific research within the next two years. This tutorial provides an in-depth overview of recent advances in AI-assisted tools and models that support and enhance the entire scientific research process, building upon findings from our recent survey paper.
We will explore how AI is revolutionizing each stage of the research cycle: (1) Literature Search and Summarization – examining AI-enhanced search systems, paper chat interfaces, graph-based knowledge discovery, and personalized recommender systems; (2) Idea Generation and Experimentation – covering LLM-based hypothesis formulation, multi-agent systems, and automated experimentation tools; (3) Multimodal Content Understanding and Generation – surveying approaches to scientific figure comprehension, automatic diagram generation from text, and poster/slide creation; (4) Text-based Content and Table Generation – reviewing models for abstracts, citations, meta-analysis tables, and long-form content like survey papers; and (5) AI-supported Peer Review – introducing automated review analysis, feedback generation, and meta-review synthesis.
Throughout the tutorial, we give due attention to critical ethical concerns, including AI hallucination, bias, limited reasoning abilities, environmental impact, and risks of fake science and plagiarism. We conclude with an interactive discussion on the challenges and opportunities of using AI in scientific research, inviting participants to imagine how AI might shape the next generation of scientific discovery while maintaining academic integrity and human authority.
Our tutorial will be held on Saturday, March 28 (all the times are based on CET = European Central Time).
@article{eger2025transforming,
title={Transforming science with large language models: A survey on ai-assisted scientific discovery, experimentation, content generation, and evaluation},
author={Eger, Steffen and Cao, Yong and D'Souza, Jennifer and Geiger, Andreas and Greisinger, Christian and Gross, Stephanie and Hou, Yufang and Krenn, Brigitte and Lauscher, Anne and Li, Yizhi and others},
journal={arXiv preprint arXiv:2502.05151},
year={2025}
}